arXiv AI

Abstraction Agent

The paper introduces the Abstraction Agent, a zero‑shot pipeline that employs a large language model to automatically generate continuous strategic features from a natural‑language game description, score private states, and cluster them into abstraction buckets without any game‑specific evaluators or training data. The pipeline consists of four phases—feature discovery with calibration anchors, batched private‑state scoring, correlation‑based feature selection, and k‑means clustering—and achieves significant reductions in lifted‑strategy exploitability in heads‑up no‑limit Texas hold’em and outperforms scalar rank baselines in ROVER Trials. The method also transfers to other games such as four‑card Pot‑Limit Omaha, HUNL preflop and flop, and Riichi Mahjong, demonstrating that it can uncover strategic concepts that align with recognized game theory insights.

arXiv AI

6d ago

Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents

The paper introduces CodeHack, a library of code-based skills with natural-language descriptions designed to improve language agents in complex environments like NetHack. By allowing agents to invoke reusable skills instead of selecting individual actions, the study shows that skill-based agents nearly triple game progression and cut inference cost by 86% in zero‑shot settings, while still retaining the option to fall back on primitive actions. In reinforcement learning, skill-based agents learn faster, achieving a 7.2× larger average gain in dungeon level within the same training budget.

By Bart{\l}omiej Cupia{\l}, Jens Tuyls, Maciej Wo{\l}czyk, Davide Paglieri, Martin Klissarov, Benjamin Eysenbach, Piotr Mi{\l}o\'s, Karthik R. Narasimhan

llms agents reinforcement-learning fine-tuning

arXiv AI

Aug 5

Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory

arXiv:2608. 03420v1 Announce Type: new Abstract: Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood.

By Jakub Rada (AI Center, Department of Computer Science, Faculty of Electrical Engineering, Czech Technical University in Prague), Viliam Lis\'y (AI Center, Department of Computer Science, Faculty of Electrical Engineering, Czech Technical University in Prague)

llms agents

arXiv AI

Jun 30

SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon CivRealm Strategy Planning

arXiv:2606. 29932v1 Announce Type: new Abstract: Long-horizon strategic planning in complex strategy games demands concurrent reasoning across multiple decision domains under imperfect information and sparse reward.

By Tianyu Jin, Shuo Chen, Yida Wang, Liuyu Xiang, Yingzhuo Liu, Zhiyao Jiang, Yexin Li, Zhaofeng He

llms agents benchmarks

arXiv AI

Jun 2

MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward Attribution

arXiv:2606. 00017v1 Announce Type: new Abstract: Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decisions made by other players.

By Aliaksei Korshuk, Alexander Buyantuev, Ilya Makarov

llms agents reinforcement-learning benchmarks

arXiv AI

Sep 23

Synthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search

The paper introduces a method for creating reactive character behaviors in continuous games as compact, human‑readable programs. It searches over a domain‑specific language that uses reactive geometric decisions and higher‑order constructs to discretize continuous behavior space, while eliminating redundant program forms through synthesis antipatterns. The approach, called agentic sketching, combines bottom‑up symbolic enumeration with top‑down guidance from a coding agent, and outperforms either technique alone on a benchmark of 14 continuous games.

By Maxim Gumin, Hsueh-Ti Derek Liu, Victor Zordan, Daniel Ritchie

agents reinforcement-learning benchmarks

arXiv AI

3d ago

STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games

arXiv:2609.38881v1 Announce Type: new Abstract: Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and att...

By Xinhe Tian, Xiaoyue Zhang, Ziyou Zhang, Jiacheng Li, Xiaoqiang Jin, Qianchuan Zhao, Gaochen Cui

llms agents efficiency

arXiv AI

Sep 17

Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization

The paper introduces Gauntlet, a framework that lets large language models autonomously build game-playing agents from a bare contract—just a game description, raw observation/action interface, and an empty policy file. In a single session, the model experiments with the game, compiles a standalone controller, and the resulting program is evaluated on held‑out instances without further model calls. The authors demonstrate that these compiled agents can win full‑scale games such as StarCraft II and Civilization, marking the first time a language‑agent system has achieved standalone victory in such complex titles.

By Joey Xiao, Haonan Huang

llms agents

arXiv AI

Sep 2

Exploring Collaboration between a language and a non-language agent

arXiv:2609.00474v1 Announce Type: cross Abstract: LLMs are increasingly deployed as orchestrators that coordinate specialized subagents to solve complex tasks through natural language. However, in ma...

By Harini S I, Somesh Singh, Yaman K Singla, Rajiv Ratn Shah, David Doermann, Balaji Krishnamurthy

llms agents robotics benchmarks

arXiv AI

Jul 9

Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1

arXiv:2607. 06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures.

By Kabir Moghe, Peter Chin

agents fine-tuning benchmarks

arXiv AI

Jul 15

Matilda: Engine-Agnostic Search with Human Policy Guidance

arXiv:2606. 25176v2 Announce Type: replace Abstract: Chess engines have evolved from search-based systems optimized solely for strength to neural policies capable of modeling human decisions across much of the rating spectrum.

By Jason Carlson

llms rag benchmarks

arXiv Machine Learning

Aug 10

Solver-Guided Reasoning for Mixed-Equilibrium Strategies

arXiv:2608. 06741v1 Announce Type: new Abstract: Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales.

By Han Wang, Philippe Beardsell, Boning Li, Aaron Sasmita, Shuai Li, Hongyuan Zha, Baoxiang Wang

llms benchmarks

arXiv Computation and Language

Aug 25

The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning

arXiv:2608.21871v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the dominant recipe for improving large language model reasoning, yet it presumes large human...

By Jing Yu, Shengchao Chen, Yiyun Tan

llms reinforcement-learning benchmarks

Related stories